我们已上线 doubao-seedance-2.5 全新模型，欢迎体验。

Doubao

Seedance 2 5

A better fit for moving from a single clip toward a complete audiovisual story: it can generate up to 30 seconds in one pass, supports multiple extensions, accepts image, video, and audio references, and adds timestamp-level editing, green-screen, and camera control. It suits ads and short films that need continuity, while complex multi-subject motion still deserves human review.

  • マルチモーダル出力

このモデルの説明は現在の言語に未対応のため、英語で表示しています。

コンソールで使うdoubao-seedance-2-5

USD

料金

default
4K
入力$5.7/1M tokens補完価格$5.7/1M tokens
video_to_video
入力$6/1M tokens補完価格$6/1M tokens
text_to_video
入力$10/1M tokens補完価格$10/1M tokens
1080p
入力$11/1M tokens補完価格$11/1M tokens

米ドル建ての公開価格です。実際の料金はアカウントグループや利用量により異なる場合があります。

API

コード例

curl --location --request POST 'https://api.tokenhot.cn/v1/video/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "doubao-seedance-2-5",
    "content": [
        {
            "type": "text",
            "text": "Use image 1 for character styling, use video 1 for camera language, and use audio 1 as background music in a cinematic product video."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://example.com/reference-image.jpg"
            },
            "role": "reference_image"
        },
        {
            "type": "audio_url",
            "audio_url": {
                "url": "https://example.com/reference-audio.mp3"
            },
            "role": "reference_audio"
        }
    ],
    "duration": 5,
    "ratio": "adaptive",
    "resolution": "720p",
    "watermark": false,
    "generate_audio": true
}'

Doubao

関連モデル

DoubaoDoubaoSeedance 2 0

A quality-first workhorse for audiovisual creation: it accepts text, image, audio, and video references, making it a fit for complex motion, multi-subject interaction, camera control, video editing, and extension. It can generate audiovisual clips up to 15 seconds with stereo audio, so it is best when visual and sound coherence matter more than the fastest turnaround.

$3.7506/1M tokensDoubaoDoubaoDreamina Seedance 2 5 Filter OFF

A strong fit for turning text or multimodal references into short videos, with 30-second single-pass generation, multi-round extension, flexible referencing, and precise editing as its main strengths. Useful for ads, short films, and connected-shot drafts, while final cuts still benefit from human selection and editing.

$5.7969/1M tokensDoubaoDoubaoSeedance 2 0 Mini

Built for video generation and multi-asset video creation, improving on Seedance 1.x with more complete motion stability, audiovisual generation, and reference inputs. Compared with Veo, Kling, and Runway, it is better suited to Chinese creative workflows driven by mixed text, image, audio, and video inputs. The Mini tier is positioned for lower-cost, high-frequency testing compared with standard Seedance 2.0. Useful for short drama, ads, e-commerce, and social assets.

$1.974/1M tokensDoubaoDoubaoSeedance 2 0 Filter OFF

This is a filter-off route name for the standard Seedance 2.0 model. The description follows the underlying model rather than treating the route suffix as a separate new model; it fits audiovisual creation with multimodal references, complex motion, camera control, and synchronized sound.

$3.7905/1M tokens

FAQ

よくある質問

Seedance 2 5 はどの用途に適していますか？

Seedance 2 5 は、このページに記載された入出力と機能に適しています。重要なシステムでは実際の負荷で事前に検証してください。

Seedance 2 5 の料金体系は？

料金は上の料金セクションに表示されています。実際の費用は利用量、アカウントグループ、リクエスト内容によって異なります。

Seedance 2 5 を呼び出すには？

上記のモデル ID と対応 API プロトコルを使用します。利用データがある場合はコード例も表示されます。

はじめる

Seedance 2 5 で構築する

コンソールで使う